© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 142304
    Prev
    Next
    INDEX
    Explanations

    coding platforms

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _{+}\
    0.38
    सन्
    0.36
     .+
    0.36
    ナム
    0.36
    ်
    0.35
     corridors
    0.34
    ƾ
    0.34
     кори
    0.34
    драт
    0.34
    ifiés
    0.34
    POSITIVE LOGITS
     longing
    0.46
     接
    0.43
    aut
    0.40
    dev
    0.40
    Henry
    0.39
    Encoding
    0.39
    mey
    0.39
    Dw
    0.38
    waiting
    0.38
     Henry
    0.38
    Activations Density 0.006%

    No Known Activations